To the best of my knowledge, FIML is ML. - Doug Bates https://stat.ethz.ch/pipermail/r-help/2004-August/056631.html

In Compact Letter Displays (CLD), groups that do not differ significantly from each other share the same letter, while groups that do show significant differences will have different letters. However, CLD's are frowned upon and probably shouldn't be used unless it's to appease someone in power, like a reviewer or advisor.

In this note I show how to suppress estimation of covariance random effects when estimating random effects for a categorical predictor.

Project for PhD Plus, session 5, 2022.

How to transform probabilities to model coefficient log-odds.

Simple example of an R Markdown report

Demonstrating that the normality assumption for linear models is for the error term (residuals), not the independent or dependent variables.

A note to accompany a blog post on hurdle models